📜Link to the paper: icml.cc/virtual/2025...
👨🏻💻Code and data: github.com/honglizhan/S...
Shout out to an amazing team @jessyjli.bsky.social, @m-yurochkin.bsky.social, Muneeza Azmat & Raya Horesh! Also super grateful to the reviewers for their invaluable feedback!
#ICML2025 #LLMAlignment
👨🏻💻Code and data: github.com/honglizhan/S...
Shout out to an amazing team @jessyjli.bsky.social, @m-yurochkin.bsky.social, Muneeza Azmat & Raya Horesh! Also super grateful to the reviewers for their invaluable feedback!
#ICML2025 #LLMAlignment
ICML Poster SPRI: Aligning Large Language Models with Context-Situated PrinciplesICML 2025
icml.cc
July 8, 2025 at 3:13 PM
📜Link to the paper: icml.cc/virtual/2025...
👨🏻💻Code and data: github.com/honglizhan/S...
Shout out to an amazing team @jessyjli.bsky.social, @m-yurochkin.bsky.social, Muneeza Azmat & Raya Horesh! Also super grateful to the reviewers for their invaluable feedback!
#ICML2025 #LLMAlignment
👨🏻💻Code and data: github.com/honglizhan/S...
Shout out to an amazing team @jessyjli.bsky.social, @m-yurochkin.bsky.social, Muneeza Azmat & Raya Horesh! Also super grateful to the reviewers for their invaluable feedback!
#ICML2025 #LLMAlignment
I’m excited to share that our paper has been accepted at #ICML2025! 🎉🥳🎊
This work was done during my internship at IBM Research, and it wouldn’t have been possible without a top-notch team and my amazing advisor 👏
This work was done during my internship at IBM Research, and it wouldn’t have been possible without a top-notch team and my amazing advisor 👏
May 2, 2025 at 9:27 PM
I’m excited to share that our paper has been accepted at #ICML2025! 🎉🥳🎊
This work was done during my internship at IBM Research, and it wouldn’t have been possible without a top-notch team and my amazing advisor 👏
This work was done during my internship at IBM Research, and it wouldn’t have been possible without a top-notch team and my amazing advisor 👏
Have you had a paper accepted to #ACL2025 or #ICML2025, or did you present at #ICLR2025? Join us at @kingscollegelondon.bsky.social on 25 June for PreTrain, building a vibrant network of #ML and #NLP scholars.
Submit proposals by 13 June and register by 18 June pretrain2025.github.io/index.html
Submit proposals by 13 June and register by 18 June pretrain2025.github.io/index.html
June 5, 2025 at 11:07 AM
Have you had a paper accepted to #ACL2025 or #ICML2025, or did you present at #ICLR2025? Join us at @kingscollegelondon.bsky.social on 25 June for PreTrain, building a vibrant network of #ML and #NLP scholars.
Submit proposals by 13 June and register by 18 June pretrain2025.github.io/index.html
Submit proposals by 13 June and register by 18 June pretrain2025.github.io/index.html
I am at #ICML2025! 🇨🇦🏞️
Catch me:
1️⃣ Presenting this paper👇 tomorrow 11am-1:30pm at East #1205
2️⃣ At the Actionable Interpretability @actinterp.bsky.social workshop on Saturday in East Ballroom A (I’m an organizer!)
Catch me:
1️⃣ Presenting this paper👇 tomorrow 11am-1:30pm at East #1205
2️⃣ At the Actionable Interpretability @actinterp.bsky.social workshop on Saturday in East Ballroom A (I’m an organizer!)
Lots of progress in mech interp (MI) lately! But how can we measure when new mech interp methods yield real improvements over prior work?
We propose 😎 𝗠𝗜𝗕: a 𝗠echanistic 𝗜nterpretability 𝗕enchmark!
We propose 😎 𝗠𝗜𝗕: a 𝗠echanistic 𝗜nterpretability 𝗕enchmark!
July 16, 2025 at 11:09 PM
I am at #ICML2025! 🇨🇦🏞️
Catch me:
1️⃣ Presenting this paper👇 tomorrow 11am-1:30pm at East #1205
2️⃣ At the Actionable Interpretability @actinterp.bsky.social workshop on Saturday in East Ballroom A (I’m an organizer!)
Catch me:
1️⃣ Presenting this paper👇 tomorrow 11am-1:30pm at East #1205
2️⃣ At the Actionable Interpretability @actinterp.bsky.social workshop on Saturday in East Ballroom A (I’m an organizer!)
Reviewing of applications will begin on Monday, Jan 19. #FAccT #FAccT2025 #CHI2025 #ACL2025 #ICML2025 #NeurIPS2025 #FAccT2026 #CHI2026 #ACL2026 #ICML2026 #NeurIPS2026
I am hiring a PhD student at the Max Planck Institute for Security and Privacy. Topics of interest: (i) AI governance/regulation through computational and socio-technical lens, (ii) computational and socio-technical approaches to digital well-being. More information & how to apply:
asiabiega.github.io
January 16, 2026 at 9:37 AM
Reviewing of applications will begin on Monday, Jan 19. #FAccT #FAccT2025 #CHI2025 #ACL2025 #ICML2025 #NeurIPS2025 #FAccT2026 #CHI2026 #ACL2026 #ICML2026 #NeurIPS2026
It's almost time! TerraBytes starts tomorrow at
@icmlconf.bsky.social 2025 in Vancouver #ICML2025
📍 08:30 West Meeting Room 111-112
🗞️ Papers are now accessible on the workshop website below the programme: terrabytes-workshop.github.io
@icmlconf.bsky.social 2025 in Vancouver #ICML2025
📍 08:30 West Meeting Room 111-112
🗞️ Papers are now accessible on the workshop website below the programme: terrabytes-workshop.github.io
July 18, 2025 at 6:38 PM
It's almost time! TerraBytes starts tomorrow at
@icmlconf.bsky.social 2025 in Vancouver #ICML2025
📍 08:30 West Meeting Room 111-112
🗞️ Papers are now accessible on the workshop website below the programme: terrabytes-workshop.github.io
@icmlconf.bsky.social 2025 in Vancouver #ICML2025
📍 08:30 West Meeting Room 111-112
🗞️ Papers are now accessible on the workshop website below the programme: terrabytes-workshop.github.io
Excited to be presenting two of our papers at #ICML2025 and workshops, today through Saturday! Topics are memory for agents, and constructing coding environments for training & evaluation. See links below:
July 16, 2025 at 6:30 PM
Excited to be presenting two of our papers at #ICML2025 and workshops, today through Saturday! Topics are memory for agents, and constructing coding environments for training & evaluation. See links below:
We’ve got a new paper out on “Learning Likelihood-free Reference Priors”, forthcoming at #ICML2025.
In this paper, we consider how reference priors (RPs) can be constructed for arbitrary simulation models. 🧵
In this paper, we consider how reference priors (RPs) can be constructed for arbitrary simulation models. 🧵
June 26, 2025 at 9:47 AM
We’ve got a new paper out on “Learning Likelihood-free Reference Priors”, forthcoming at #ICML2025.
In this paper, we consider how reference priors (RPs) can be constructed for arbitrary simulation models. 🧵
In this paper, we consider how reference priors (RPs) can be constructed for arbitrary simulation models. 🧵
🚨 Thrilled to share our #ICML2025 paper: "Sable: a Performant, Efficient and Scalable Sequence Model for MARL"!
We introduce a new SOTA cooperative Multi-Agent Reinforcement Learning algorithm that delivers the advantages of centralised learning without its drawbacks.
(1/N)
We introduce a new SOTA cooperative Multi-Agent Reinforcement Learning algorithm that delivers the advantages of centralised learning without its drawbacks.
(1/N)
July 14, 2025 at 3:40 PM
🚨 Thrilled to share our #ICML2025 paper: "Sable: a Performant, Efficient and Scalable Sequence Model for MARL"!
We introduce a new SOTA cooperative Multi-Agent Reinforcement Learning algorithm that delivers the advantages of centralised learning without its drawbacks.
(1/N)
We introduce a new SOTA cooperative Multi-Agent Reinforcement Learning algorithm that delivers the advantages of centralised learning without its drawbacks.
(1/N)
🚨 Poster at #ICML2025!
How can LLMs really keep up with the world?
Come by E-2405 on July 15th (4:30–7:00pm) to check out WikiBigEdit – our new benchmark to test lifelong knowledge editing in LLMs at scale.
🔗 Real-world updates
📈 500k+ QA edits
🧠 Editing vs. RAG vs. CL
How can LLMs really keep up with the world?
Come by E-2405 on July 15th (4:30–7:00pm) to check out WikiBigEdit – our new benchmark to test lifelong knowledge editing in LLMs at scale.
🔗 Real-world updates
📈 500k+ QA edits
🧠 Editing vs. RAG vs. CL
July 14, 2025 at 4:58 PM
🚨 Poster at #ICML2025!
How can LLMs really keep up with the world?
Come by E-2405 on July 15th (4:30–7:00pm) to check out WikiBigEdit – our new benchmark to test lifelong knowledge editing in LLMs at scale.
🔗 Real-world updates
📈 500k+ QA edits
🧠 Editing vs. RAG vs. CL
How can LLMs really keep up with the world?
Come by E-2405 on July 15th (4:30–7:00pm) to check out WikiBigEdit – our new benchmark to test lifelong knowledge editing in LLMs at scale.
🔗 Real-world updates
📈 500k+ QA edits
🧠 Editing vs. RAG vs. CL
Back from #ICML2025 🛬, and off 🚄 to Norrköping 🇸🇪 for #ic2s2
CLAN (cs.au.dk/~clan/) members are presenting 2 papers: 1 spotlight and 1 oral. See 🧵for posters and summaries
👋 Reach out to chat about observational studies, causality, LLM agents, human-centered AI etc.
CLAN (cs.au.dk/~clan/) members are presenting 2 papers: 1 spotlight and 1 oral. See 🧵for posters and summaries
👋 Reach out to chat about observational studies, causality, LLM agents, human-centered AI etc.
CLAN for AI Research on Language and Networks
CLAN for AI Research on Language and Networks, or **CLAN** for short, is a research group and a part of the larger [DIS Group](https://cs.au.dk/research/data-intensive-systems) in the [Department of C...
cs.au.dk
July 21, 2025 at 8:09 AM
Back from #ICML2025 🛬, and off 🚄 to Norrköping 🇸🇪 for #ic2s2
CLAN (cs.au.dk/~clan/) members are presenting 2 papers: 1 spotlight and 1 oral. See 🧵for posters and summaries
👋 Reach out to chat about observational studies, causality, LLM agents, human-centered AI etc.
CLAN (cs.au.dk/~clan/) members are presenting 2 papers: 1 spotlight and 1 oral. See 🧵for posters and summaries
👋 Reach out to chat about observational studies, causality, LLM agents, human-centered AI etc.
Members of the CLAN (cs.au.dk/~clan/) are excited to be in Vancouver 🇨🇦 this week to present two papers at #ICML2025 @icmlconf.bsky.social 🌲☕🛰️
👋 Reach out if you're curious about multi-agent LLMs, scalable reasoning, AI efficiency, human-centered AI, or just want to chat systems/ML
🧵1/n
👋 Reach out if you're curious about multi-agent LLMs, scalable reasoning, AI efficiency, human-centered AI, or just want to chat systems/ML
🧵1/n
CLAN for AI Research on Language and Networks
CLAN for AI Research on Language and Networks, or **CLAN** for short, is a research group and a part of the larger [DIS Group](https://cs.au.dk/research/data-intensive-systems) in the [Department of C...
cs.au.dk
July 14, 2025 at 3:09 PM
Members of the CLAN (cs.au.dk/~clan/) are excited to be in Vancouver 🇨🇦 this week to present two papers at #ICML2025 @icmlconf.bsky.social 🌲☕🛰️
👋 Reach out if you're curious about multi-agent LLMs, scalable reasoning, AI efficiency, human-centered AI, or just want to chat systems/ML
🧵1/n
👋 Reach out if you're curious about multi-agent LLMs, scalable reasoning, AI efficiency, human-centered AI, or just want to chat systems/ML
🧵1/n
そういえば、ICML参加する人いたらこのWSに遊びに行くと楽しいと思います。
（しれっとprogram committeeに入ってる）
vecdb-ws.github.io/icml2025/ind...
（しれっとprogram committeeに入ってる）
vecdb-ws.github.io/icml2025/ind...
VecDB@ICML2025
vecdb-ws.github.io
June 17, 2025 at 5:34 PM
そういえば、ICML参加する人いたらこのWSに遊びに行くと楽しいと思います。
（しれっとprogram committeeに入ってる）
vecdb-ws.github.io/icml2025/ind...
（しれっとprogram committeeに入ってる）
vecdb-ws.github.io/icml2025/ind...
Excited to be chatting about our new paper "Understanding Fixed Predictions via Confined Regions" (joint work with @berkustun.bsky.social, Lily Weng, and Madeleine Udell) at #ICML2025!
🕐 Wed 16 Jul 4:30 p.m. PDT — 7 p.m. PDT
📍East Exhibition Hall A-B #E-1104
🔗 arxiv.org/abs/2502.16380
🕐 Wed 16 Jul 4:30 p.m. PDT — 7 p.m. PDT
📍East Exhibition Hall A-B #E-1104
🔗 arxiv.org/abs/2502.16380
Understanding Fixed Predictions via Confined Regions
Machine learning models can assign fixed predictions that preclude individuals from changing their outcome. Existing approaches to audit fixed predictions do so on a pointwise basis, which requires ac...
arxiv.org
July 14, 2025 at 4:08 PM
Excited to be chatting about our new paper "Understanding Fixed Predictions via Confined Regions" (joint work with @berkustun.bsky.social, Lily Weng, and Madeleine Udell) at #ICML2025!
🕐 Wed 16 Jul 4:30 p.m. PDT — 7 p.m. PDT
📍East Exhibition Hall A-B #E-1104
🔗 arxiv.org/abs/2502.16380
🕐 Wed 16 Jul 4:30 p.m. PDT — 7 p.m. PDT
📍East Exhibition Hall A-B #E-1104
🔗 arxiv.org/abs/2502.16380
Discover the latest advances in deep learning theory at WiML @ ICML 2025 with invited speaker Leena Vankadara, Lecturer at the Gatsby Unit, UCL.
A must-attend for anyone interested in the future of AI and the science behind scaling large models.
#WiML #ICML2025 #DeepLearning
A must-attend for anyone interested in the future of AI and the science behind scaling large models.
#WiML #ICML2025 #DeepLearning
July 15, 2025 at 11:20 PM
Discover the latest advances in deep learning theory at WiML @ ICML 2025 with invited speaker Leena Vankadara, Lecturer at the Gatsby Unit, UCL.
A must-attend for anyone interested in the future of AI and the science behind scaling large models.
#WiML #ICML2025 #DeepLearning
A must-attend for anyone interested in the future of AI and the science behind scaling large models.
#WiML #ICML2025 #DeepLearning
Discover how AI is transforming environmental forecasting at WiML @ ICML 2025 with invited speaker Ana Lucic!
A must-attend for anyone interested in the future of AI for climate and environmental science.
#WiML #ICML2025 #ClimateAI #MachineLearning #WomenInML #AI4Earth
A must-attend for anyone interested in the future of AI for climate and environmental science.
#WiML #ICML2025 #ClimateAI #MachineLearning #WomenInML #AI4Earth
July 15, 2025 at 11:20 PM
Discover how AI is transforming environmental forecasting at WiML @ ICML 2025 with invited speaker Ana Lucic!
A must-attend for anyone interested in the future of AI for climate and environmental science.
#WiML #ICML2025 #ClimateAI #MachineLearning #WomenInML #AI4Earth
A must-attend for anyone interested in the future of AI for climate and environmental science.
#WiML #ICML2025 #ClimateAI #MachineLearning #WomenInML #AI4Earth
We’re excited to kick off the Invited Talk Series at WiML @ ICML 2025 with Sarah Schwettmann, Co-Founder of Transluce and Research Scientist at MIT CSAIL.
Join us to explore how AI can help us understand itself.
#WiML #ICML2025 #AI #Interpretability #WomenInML #MachineLearning
Join us to explore how AI can help us understand itself.
#WiML #ICML2025 #AI #Interpretability #WomenInML #MachineLearning
July 15, 2025 at 11:20 PM
We’re excited to kick off the Invited Talk Series at WiML @ ICML 2025 with Sarah Schwettmann, Co-Founder of Transluce and Research Scientist at MIT CSAIL.
Join us to explore how AI can help us understand itself.
#WiML #ICML2025 #AI #Interpretability #WomenInML #MachineLearning
Join us to explore how AI can help us understand itself.
#WiML #ICML2025 #AI #Interpretability #WomenInML #MachineLearning
How do researchers turn papers into real-world impact?
At the WiML Symposium @ ICML 2025, join Microsoft’s Ida Momennejad and Yuhang He for a roundtable on academic-industry collaboration.
🗓 July 16 | 1–2 PM PT | Vancouver
#WiML #ICML2025 #MLResearch
At the WiML Symposium @ ICML 2025, join Microsoft’s Ida Momennejad and Yuhang He for a roundtable on academic-industry collaboration.
🗓 July 16 | 1–2 PM PT | Vancouver
#WiML #ICML2025 #MLResearch
July 14, 2025 at 3:05 PM
How do researchers turn papers into real-world impact?
At the WiML Symposium @ ICML 2025, join Microsoft’s Ida Momennejad and Yuhang He for a roundtable on academic-industry collaboration.
🗓 July 16 | 1–2 PM PT | Vancouver
#WiML #ICML2025 #MLResearch
At the WiML Symposium @ ICML 2025, join Microsoft’s Ida Momennejad and Yuhang He for a roundtable on academic-industry collaboration.
🗓 July 16 | 1–2 PM PT | Vancouver
#WiML #ICML2025 #MLResearch
Curious about careers in quantitative finance?
Join Ding Zhou and Yanyao Shen from Two Sigma at the WiML Symposium @ ICML 2025 for the roundtable session “From a PhD to Quantitative Research”.
🗓 July 16 | 1–2 PM PT
📍 Vancouver Convention Center
Don’t miss it!
#ICML #WiML #ICML2025
Join Ding Zhou and Yanyao Shen from Two Sigma at the WiML Symposium @ ICML 2025 for the roundtable session “From a PhD to Quantitative Research”.
🗓 July 16 | 1–2 PM PT
📍 Vancouver Convention Center
Don’t miss it!
#ICML #WiML #ICML2025
July 11, 2025 at 8:17 PM
Excited to share our paper "Subgoal-Guided Policy Heuristic Search with Learned Subgoals" has been accepted to #icml2025!
Paper Preview: arxiv.org/pdf/2506.07255
I'll be attending ICML-25 in Vancouver, and I'm looking forward to chatting with anyone who is interested in our work!
Paper Preview: arxiv.org/pdf/2506.07255
I'll be attending ICML-25 in Vancouver, and I'm looking forward to chatting with anyone who is interested in our work!
arxiv.org
June 10, 2025 at 4:34 PM
Excited to share our paper "Subgoal-Guided Policy Heuristic Search with Learned Subgoals" has been accepted to #icml2025!
Paper Preview: arxiv.org/pdf/2506.07255
I'll be attending ICML-25 in Vancouver, and I'm looking forward to chatting with anyone who is interested in our work!
Paper Preview: arxiv.org/pdf/2506.07255
I'll be attending ICML-25 in Vancouver, and I'm looking forward to chatting with anyone who is interested in our work!